中文(ZH) 阶跃发布 StepAudio 3 ，多款语音模型登顶 Artificial Analysis 全球榜单

Jieyue launches StepAudio 3 voice models, topping global AI rankings

By PulseAugur Editorial · [1 sources] · 2026-09-15 09:50

Jieyue (Step) has launched its new generation of large voice models, the StepAudio 3 series, featuring five distinct models: StepAudio 3 Realtime, StepAudio 3 ASR, StepAudio 3 TTS, StepAudio 3 Gen, and StepAudio 3 Music. These models cover a wide range of applications including real-time voice interaction, speech recognition, realistic voice generation, and music creation. Notably, several of these models have achieved top global rankings on the Artificial Analysis benchmark, demonstrating advanced capabilities in areas like conversational dynamics and speech reasoning. AI

IMPACT Sets new benchmarks for voice AI capabilities, potentially accelerating adoption in real-time interaction and content creation.

RANK_REASON New model release from a significant AI lab with benchmark claims. [lever_c_demoted from frontier_release: ic=1 ai=1.0]

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

How we ranked this

Signal score: 33 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Significant; New model release from a significant AI lab with benchmark claims. [lever_c_demoted from frontier_release: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: model release, product; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

Full methodology in our editorial standards.

雷峰网 (Leiphone) TIER_1 中文(ZH) · 2026-09-15 09:50

Jieyue Release StepAudio 3, Multiple Voice Models Top Artificial Analysis Global Rankings

<p> <span style="font-family: Arial; font-size: 11pt;">9月15日，阶跃发布新一代语音大模型 StepAudio 3 系列，一次性推出 StepAudio 3 Realtime、StepAudio 3 ASR、StepAudio 3 TTS、StepAudio 3 Gen 和 StepAudio 3 Music 五款模型，覆盖实时语音交互、语音识别、真人级语音生成和音乐创作等场景。其中，多款模型在</span><span style="font-family: Arial; font-siz…